Implementation notes: x86, h4e450, crypto_aead/scream10v2

Computer: h4e450
Architecture: x86
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: scream10v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
717943refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2017101020170725
720224refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2017101020170725
724185refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2017101020170725
725016refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2017101020170725
728945refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2017101020170725
741613refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2017101020170725
745237refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2017101020170725
746187refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2017101020170725
749256refgcc -m32 -O3 -fomit-frame-pointer2017101020170725
750353refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2017101020170725
751830refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2017101020170725
752466refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2017101020170725
762565refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2017101020170725
762755refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2017101020170725
765990refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2017101020170725
767785refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2017101020170725
768317refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2017101020170725
768560refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2017101020170725
769814refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2017101020170725
770018refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2017101020170725
770768refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2017101020170725
773119refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2017101020170725
778862refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017101020170725
778971refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2017101020170725
779156refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2017101020170725
779974refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2017101020170725
783797refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2017101020170725
785741refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2017101020170725
788067refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2017101020170725
788538refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2017101020170725
788728refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2017101020170725
790566refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2017101020170725
790742refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2017101020170725
792775refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2017101020170725
793136refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2017101020170725
796248refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2017101020170725
796309refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2017101020170725
796480refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2017101020170725
796898refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2017101020170725
796989refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2017101020170725
798147refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2017101020170725
800309refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017101020170725
800337refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2017101020170725
803049refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2017101020170725
804963refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2017101020170725
813642refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2017101020170725
815091refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2017101020170725
815229refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2017101020170725
815879refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2017101020170725
815917refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2017101020170725
815974refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2017101020170725
828215refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2017101020170725
828913refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017101020170725
834062refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2017101020170725
835402refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2017101020170725
836171refgcc -funroll-loops -m32 -O -fomit-frame-pointer2017101020170725
843348refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2017101020170725
846740refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2017101020170725
847101refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2017101020170725
847885refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2017101020170725
850288refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2017101020170725
860995refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2017101020170725
875173refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2017101020170725
881481refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2017101020170725
886977refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2017101020170725
887162refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2017101020170725
899351refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2017101020170725
901702refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2017101020170725
901921refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2017101020170725
910219refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2017101020170725
910366refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2017101020170725
910765refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2017101020170725
927717refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017101020170725
928083refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2017101020170725
943535refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2017101020170725
948528refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2017101020170725
951686refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2017101020170725
952731refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2017101020170725
952745refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017101020170725
953544refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2017101020170725
955510refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2017101020170725
962588refgcc -m32 -O2 -fomit-frame-pointer2017101020170725
974007refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2017101020170725
985482refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2017101020170725
989563refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2017101020170725
989962refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2017101020170725
990565refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2017101020170725
1025491refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2017101020170725
1025696refgcc -m32 -march=nocona -O -fomit-frame-pointer2017101020170725
1030308refgcc -m32 -march=barcelona -O -fomit-frame-pointer2017101020170725
1035571refgcc -m32 -march=prescott -O -fomit-frame-pointer2017101020170725
1036707refgcc -m32 -march=athlon -O -fomit-frame-pointer2017101020170725
1046397refgcc -m32 -march=corei7 -O -fomit-frame-pointer2017101020170725
1046767refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2017101020170725
1046772refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2017101020170725
1046819refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2017101020170725
1047138refgcc -m32 -march=i486 -O -fomit-frame-pointer2017101020170725
1047850refgcc -m32 -O -fomit-frame-pointer2017101020170725
1048828refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2017101020170725
1052710refgcc -m32 -march=k8 -O -fomit-frame-pointer2017101020170725
1055412refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2017101020170725
1061445refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2017101020170725
1065739refgcc -m32 -march=core2 -O -fomit-frame-pointer2017101020170725
1067031refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2017101020170725
1071510refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2017101020170725
1072968refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2017101020170725
1075200refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2017101020170725
1076369refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2017101020170725
1080601refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2017101020170725
1081157refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2017101020170725
1081803refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2017101020170725
1089160refgcc -m32 -march=i386 -O -fomit-frame-pointer2017101020170725
1093854refgcc -m32 -march=k6 -O -fomit-frame-pointer2017101020170725
1093939refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2017101020170725
1094115refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2017101020170725
1096747refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2017101020170725
1097322refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2017101020170725
1098599refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2017101020170725
1102090refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2017101020170725
1113101refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017101020170725
1116464refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2017101020170725
1116568refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2017101020170725
1120116refgcc -m32 -march=pentium -O -fomit-frame-pointer2017101020170725
1126491refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2017101020170725
1130044refgcc -m32 -march=i486 -Os -fomit-frame-pointer2017101020170725
1130078refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2017101020170725
1130139refgcc -m32 -march=pentium -Os -fomit-frame-pointer2017101020170725
1130762refgcc -m32 -march=i386 -Os -fomit-frame-pointer2017101020170725
1131493refgcc -m32 -march=prescott -Os -fomit-frame-pointer2017101020170725
1131687refgcc -m32 -march=nocona -Os -fomit-frame-pointer2017101020170725
1132609refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2017101020170725
1144379refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2017101020170725
1145562refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2017101020170725
1146949refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2017101020170725
1147134refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2017101020170725
1149600refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2017101020170725
1149747refgcc -m32 -march=core2 -Os -fomit-frame-pointer2017101020170725
1156041refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017101020170725
1156241refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2017101020170725
1156967refgcc -m32 -Os -fomit-frame-pointer2017101020170725
1157176refgcc -m32 -march=athlon -Os -fomit-frame-pointer2017101020170725
1163403refgcc -m32 -march=k8 -Os -fomit-frame-pointer2017101020170725
1163422refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2017101020170725
1163456refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2017101020170725
1173174refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2017101020170725
1173402refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2017101020170725
1186094refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2017101020170725
1190554refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2017101020170725
1192112refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2017101020170725
1195641refgcc -m32 -march=k6 -Os -fomit-frame-pointer2017101020170725
1195827refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2017101020170725
1196743refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2017101020170725
1199893refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2017101020170725
1227115refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2017101020170725
1227158refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2017101020170725
1237618refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2017101020170725
1248304refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2017101020170725
1248334refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2017101020170725
1254812refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2017101020170725
1264555refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2017101020170725
1272396refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2017101020170725

Test failure

Implementation: crypto_aead/scream10v2/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 35, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer ref sse
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer ref sse
gcc -m32 -march=core2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=core2 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -Os -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer sse
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer sse
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer ref sse
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer ref sse
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer ref sse
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer sse
gcc -m32 -march=corei7 -O -fomit-frame-pointer sse
gcc -m32 -march=corei7 -Os -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer sse
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream10v2/sse
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:16:32: warning: implicit declaration of function '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:182:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:182:5: error: can't convert between vector values of different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:183:5: error: can't convert between vector values of different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 96, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer sse
gcc -m32 -O2 -fomit-frame-pointer sse
gcc -m32 -O3 -fomit-frame-pointer sse
gcc -m32 -O -fomit-frame-pointer sse
gcc -m32 -Os -fomit-frame-pointer sse
gcc -m32 -march=athlon -O2 -fomit-frame-pointer sse
gcc -m32 -march=athlon -O3 -fomit-frame-pointer sse
gcc -m32 -march=athlon -O -fomit-frame-pointer sse
gcc -m32 -march=athlon -Os -fomit-frame-pointer sse
gcc -m32 -march=i386 -O2 -fomit-frame-pointer sse
gcc -m32 -march=i386 -O3 -fomit-frame-pointer sse
gcc -m32 -march=i386 -O -fomit-frame-pointer sse
gcc -m32 -march=i386 -Os -fomit-frame-pointer sse
gcc -m32 -march=i486 -O2 -fomit-frame-pointer sse
gcc -m32 -march=i486 -O3 -fomit-frame-pointer sse
gcc -m32 -march=i486 -O -fomit-frame-pointer sse
gcc -m32 -march=i486 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -O -fomit-frame-pointer sse
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -O -fomit-frame-pointer sse
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer sse
gcc -m32 -march=k6 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k6 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k6 -O -fomit-frame-pointer sse
gcc -m32 -march=k6 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer sse
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium -O -fomit-frame-pointer sse
gcc -m32 -march=pentium -Os -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer sse
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream10v2/sse
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 44, namely:
CompilerImplementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer sse
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer sse
gcc -m32 -march=k8 -O2 -fomit-frame-pointer sse
gcc -m32 -march=k8 -O3 -fomit-frame-pointer sse
gcc -m32 -march=k8 -O -fomit-frame-pointer sse
gcc -m32 -march=k8 -Os -fomit-frame-pointer sse
gcc -m32 -march=nocona -O2 -fomit-frame-pointer sse
gcc -m32 -march=nocona -O3 -fomit-frame-pointer sse
gcc -m32 -march=nocona -O -fomit-frame-pointer sse
gcc -m32 -march=nocona -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -O -fomit-frame-pointer sse
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -O -fomit-frame-pointer sse
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer sse
gcc -m32 -march=prescott -O2 -fomit-frame-pointer sse
gcc -m32 -march=prescott -O3 -fomit-frame-pointer sse
gcc -m32 -march=prescott -O -fomit-frame-pointer sse
gcc -m32 -march=prescott -Os -fomit-frame-pointer sse

Compiler output

Implementation: crypto_aead/scream10v2/sse
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:191:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: D = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:198:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: A ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: scream.c:199:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: C ^= __builtin_ia32_pshufb128(table, in[2]);
scream.c: ^
scream.c: scream.c:203:7: error: conversion of scalar 'int' to vector 'v16qi {aka __vector(16) char}' involves truncation
scream.c: B ^= __builtin_ia32_pshufb128(table, in[0]);
scream.c: ^
scream.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer sse
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer sse
gcc -m32 -march=barcelona -O -fomit-frame-pointer sse
gcc -m32 -march=barcelona -Os -fomit-frame-pointer sse